arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1809.00699cs.CL
收藏

用于远程监督关系抽取的多层结构化自注意

Multi-Level Structured Self-Attentions for Distantly Supervised Relation Extraction

ADAPT Centre, School of Computing, Dublin City University(都柏林城市大学计算学院ADAPT中心);Accenture Labs Dublin(埃森哲都柏林实验室)

Jinhua Du, Jingguang Han, Andy Way, Dadong Wan

摘要:

注意力机制经常在深度神经网络中用于远距离监督关系抽取(DS-RE),以区分有效实例和噪声实例。然而,传统的1-D向量注意力模型是不够的学习不同的背景下,选择有效的实例来预测实体对的关系。为了缓解这个问题,我们提出了一种新的多层结构(2-D矩阵)的自我注意力机制DS-RE在多实例学习(MIL)框架使用双向递归神经网络。在所提出的方法中,一个结构化的单词级自我注意力机制学习一个2-D矩阵,其中每个行向量表示关于两个实体的实例的不同方面的权重分布。针对MIL问题,结构化的中间层注意力学习一个二维矩阵,其中每个行向量表示选择不同有效实例时的权重分布。在两个公开的DS-RE数据集上进行的实验表明,所提出的具有多层次结构化自我注意力机制的框架在PR曲线、P@N和F1测量方面显著优于最先进的基线。

英文摘要:

Attention mechanisms are often used in deep neural networks for distantly supervised relation extraction (DS-RE) to distinguish valid from noisy instances. However, traditional 1-D vector attention models are insufficient for the learning of different contexts in the selection of valid instances to predict the relationship for an entity pair. To alleviate this issue, we propose a novel multi-level structured (2-D matrix) self-attention mechanism for DS-RE in a multi-instance learning (MIL) framework using bidirectional recurrent neural networks. In the proposed method, a structured word-level self-attention mechanism learns a 2-D matrix where each row vector represents a weight distribution for different aspects of an instance regarding two entities. Targeting the MIL issue, the structured sentence-level attention learns a 2-D matrix where each row vector represents a weight distribution on selection of different valid in-stances. Experiments conducted on two publicly available DS-RE datasets show that the proposed framework with a multi-level structured self-attention mechanism significantly outperform state-of-the-art baselines in terms of PR curves, P@N and F1 measures.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑